Complete Tensorflow 2 and Keras Deep Learning Bootcamp

Complete Tensorflow 2 and Keras Deep Learning Bootcamp

English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 19 Hours | 6.74 GB

Learn to use Python for Deep Learning with Google’s latest Tensorflow 2 library and Keras!

This course will guide you through how to use Google’s latest TensorFlow 2 framework to create artificial neural networks for deep learning! This course aims to give you an easy to understand guide to the complexities of Google’s TensorFlow 2 framework in a way that is easy to understand.

We’ll focus on understanding the latest updates to TensorFlow and leveraging the Keras API (TensorFlow 2.0’s official API) to quickly and easily build models. In this course we will build models to forecast future price homes, classify medical images, predict future sales data, generate complete new text artificially and much more!

This course is designed to balance theory and practical implementation, with complete jupyter notebook guides of code and easy to reference slides and notes. We also have plenty of exercises to test your new skills along the way!

This course covers a variety of topics, including

  • NumPy Crash Course
  • Pandas Data Analysis Crash Course
  • Data Visualization Crash Course
  • Neural Network Basics
  • TensorFlow Basics
  • Keras Syntax Basics
  • Artificial Neural Networks
  • Densely Connected Networks
  • Convolutional Neural Networks
  • Recurrent Neural Networks
  • AutoEncoders
  • GANs – Generative Adversarial Networks
  • Deploying TensorFlow into Production
  • and much more!

Keras, a user-friendly API standard for machine learning, will be the central high-level API used to build and train models. The Keras API makes it easy to get started with TensorFlow 2. Importantly, Keras provides several model-building APIs (Sequential, Functional, and Subclassing), so you can choose the right level of abstraction for your project. TensorFlow’s implementation contains enhancements including eager execution, for immediate iteration and intuitive debugging, and, for building scalable input pipelines.

TensorFlow 2 makes it easy to take new ideas from concept to code, and from model to publication. TensorFlow 2.0 incorporates a number of features that enables the definition and training of state of the art models without sacrificing speed or performance

It is used by major companies all over the world, including Airbnb, Ebay, Dropbox, Snapchat, Twitter, Uber, SAP, Qualcomm, IBM, Intel, and of course, Google!

Become a deep learning guru today! We’ll see you inside the course!

What you’ll learn

  • Learn to use TensorFlow 2.0 for Deep Learning
  • Leverage the Keras API to quickly build models that run on Tensorflow 2
  • Perform Image Classification with Convolutional Neural Networks
  • Use Deep Learning for medical imaging
  • Forecast Time Series data with Recurrent Neural Networks
  • Use Generative Adversarial Networks (GANs) to generate images
  • Use deep learning for style transfer
  • Generate text with RNNs and Natural Language Processing
  • Serve Tensorflow Models through an API
  • Use GPUs for accelerated deep learning
Table of Contents

Course Overview Installs and Setup
1 Course Overview
2 Course Setup and Installation
3 FAQ – Frequently Asked Questions

NumPy Crash Course
4 Introduction to NumPy
5 NumPy Arrays
6 Numpy Index Selection
7 NumPy Operations
8 NumPy Exercises
9 Numpy Exercises – Solutions

Pandas Crash Course
10 Introduction to Pandas
11 Pandas Series
12 Pandas DataFrames – Part One
13 Pandas DataFrames – Part Two
14 Pandas Missing Data
15 GroupBy Operations
16 Pandas Operations
17 Data Input and Output
18 Pandas Exercises
19 Pandas Exercises – Solutions

Visualization Crash Course
20 Introduction to Python Visualization
21 Matplotlib Basics
22 Seaborn Basics
23 Data Visualization Exercises
24 Data Visualization Exercises – Solutions

Machine Learning Concepts Overview
25 What is Machine Learning
26 Supervised Learning Overview
27 Overfitting
28 Evaluating Performance – Classification Error Metrics
29 Evaluating Performance – Regression Error Metrics
30 Unsupervised Learning

Basic Artificial Neural Networks – ANNs
31 Introduction to ANN Section
32 Perceptron Model
33 Neural Networks
34 Activation Functions
35 Multi-Class Classification Considerations
36 Cost Functions and Gradient Descent
37 Backpropagation
38 TensorFlow vs. Keras Explained
39 Keras Syntax Basics – Part One – Preparing the Data
40 Keras Syntax Basics – Part Two – Creating and Training the Model
41 Keras Syntax Basics – Part Three – Model Evaluation
42 Keras Regression Code Along – Exploratory Data Analysis
43 Keras Regression Code Along – Exploratory Data Analysis – Continued
44 Keras Regression Code Along – Data Preprocessing and Creating a Model
45 Keras Regression Code Along – Model Evaluation and Predictions
46 Keras Classification Code Along – EDA and Preprocessing
47 Keras Classification – Dealing with Overfitting and Evaluation
48 TensorFlow 2.0 Keras Project Options Overview
49 TensorFlow 2.0 Keras Project Notebook Overview
50 Keras Project Solutions – Exploratory Data Analysis
51 Keras Project Solutions – Dealing with Missing Data
52 Keras Project Solutions – Dealing with Missing Data – Part Two
53 Keras Project Solutions – Categorical Data
54 Keras Project Solutions – Data PreProcessing
55 Keras Project Solutions – Creating and Training a Model
56 Keras Project Solutions – Model Evaluation
57 Tensorboard

Convolutional Neural Networks – CNNs
58 CNN Section Overview
59 Image Filters and Kernels
60 Convolutional Layers
61 Pooling Layers
62 MNIST Data Set Overview
63 CNN on MNIST – Part One – The Data
64 CNN on MNIST – Part Two – Creating and Training the Model
65 CNN on MNIST – Part Three – Model Evaluation
66 CNN on CIFAR-10 – Part One – The Data
67 CNN on CIFAR-10 – Part Two – Evaluating the Model
68 Downloading Data Set for Real Image Lectures
69 CNN on Real Image Files – Part One – Reading in the Data
70 CNN on Real Image Files – Part Two – Data Processing
71 CNN on Real Image Files – Part Three – Creating the Model
72 CNN on Real Image Files – Part Four – Evaluating the Model
73 CNN Exercise Overview
74 CNN Exercise Solutions

Recurrent Neural Networks – RNNs
75 RNN Section Overview
76 RNN Basic Theory
77 Vanishing Gradients
78 LSTMS and GRU
79 RNN Batches
80 RNN on a Sine Wave – The Data
81 RNN on a Sine Wave – Batch Generator
82 RNN on a Sine Wave – Creating the Model
83 RNN on a Sine Wave – LSTMs and Forecasting
84 RNN on a Time Series – Part One
85 RNN on a Time Series – Part Two
86 RNN Exercise
87 RNN Exercise – Solutions
88 Bonus – Multivariate Time Series – RNN and LSTMs

Natural Language Processing
89 Introduction to NLP Section
90 NLP – Part One – The Data
91 NLP – Part Two – Text Processing
92 NLP – Part Three – Creating Batches
93 NLP – Part Four – Creating the Model
94 NLP – Part Five – Training the Model
95 NLP – Part Six – Generating Text

96 Introduction to Autoencoders
97 Autoencoder Basics
98 Autoencoder for Dimensionality Reduction
99 Autoencoder for Images – Part One
100 Autoencoder for Images – Part Two – Noise Removal
101 Autoencoder Exercise Overview
102 Autoencoder Exercise – Solutions

Generative Adversarial Networks
103 GANs Overview
104 Creating a GAN – Part One- The Data
105 Creating a GAN – Part Two – The Model
106 Creating a GAN – Part Three – Model Training
107 DCGAN – Deep Convolutional Generative Adversarial Networks

108 Introduction to Deployment
109 Creating the Model
110 Model Prediction Function
111 Running a Basic Flask Application
112 Flask Postman API
113 Flask API – Using Requests Programmatically
114 Flask Front End
115 Live Deployment to the Web